{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:30Z","timestamp":1772138070890,"version":"3.50.1"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R35GM142701"],"award-info":[{"award-number":["R35GM142701"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>5-Hydroxymethylcytosine (5hmC), a crucial epigenetic mark with a significant role in regulating tissue-specific gene expression, is essential for understanding the dynamic functions of the human genome. Despite its importance, predicting 5hmC modification across the genome remains a challenging task, especially when considering the complex interplay between DNA sequences and various epigenetic factors such as histone modifications and chromatin accessibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using tissue-specific 5hmC sequencing data, we introduce Deep5hmC, a multimodal deep learning framework that integrates both the DNA sequence and epigenetic features such as histone modification and chromatin accessibility to predict genome-wide 5hmC modification. The multimodal design of Deep5hmC demonstrates remarkable improvement in predicting both qualitative and quantitative 5hmC modification compared to unimodal versions of Deep5hmC and state-of-the-art machine learning methods. This improvement is demonstrated through benchmarking on a comprehensive set of 5hmC sequencing data collected at four developmental stages during forebrain organoid development and across 17 human tissues. Compared to DeepSEA and random forest, Deep5hmC achieves close to 4% and 17% improvement of Area Under the Receiver Operating Characteristic (AUROC) across four forebrain developmental stages, and 6% and 27% across 17 human tissues for predicting binary 5hmC modification sites; and 8% and 22% improvement of Spearman correlation coefficient across four forebrain developmental stages, and 17% and 30% across 17 human tissues for predicting continuous 5hmC modification. Notably, Deep5hmC showcases its practical utility by accurately predicting gene expression and identifying differentially hydroxymethylated regions (DhMRs) in a case\u2013control study of Alzheimer\u2019s disease (AD). Deep5hmC significantly improves our understanding of tissue-specific gene regulation and facilitates the development of new biomarkers for complex diseases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Deep5hmC is available via https:\/\/github.com\/lichen-lab\/Deep5hmC<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae528","type":"journal-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T16:16:10Z","timestamp":1724861770000},"source":"Crossref","is-referenced-by-count":3,"title":["Deep5hmC: predicting genome-wide 5-hydroxymethylcytosine landscape via a multimodal deep learning model"],"prefix":"10.1093","volume":"40","author":[{"given":"Xin","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Biostatistics, University of Florida , Gainesville, FL 32603, United States"}]},{"given":"Sai Ritesh","family":"Thela","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Florida , Gainesville, FL 32603, United States"}]},{"given":"Fengdi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Florida , Gainesville, FL 32603, United States"}]},{"given":"Bing","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Human Genetics, Emory University School of Medicine , Atlanta, GA 30322, United States"}]},{"given":"Zhexing","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Emory University School of Medicine , Atlanta, GA 30322, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6137-6659","authenticated-orcid":false,"given":"Peng","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Human Genetics, Emory University School of Medicine , Atlanta, GA 30322, United States"}]},{"given":"Jinying","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, University of Florida , Gainesville, FL 32603, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9372-5606","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Florida , Gainesville, FL 32603, United States"}]}],"member":"286","published-online":{"date-parts":[[2024,8,28]]},"reference":[{"key":"2024090622303213500_btae528-B1","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad060","article-title":"TIVAN-indel: a computational framework for annotating and predicting non-coding regulatory small insertions and deletions","volume":"39","author":"Agarwal","year":"2023","journal-title":"Bioinformatics"},{"key":"2024090622303213500_btae528-B2","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1016\/j.csbj.2020.10.032","article-title":"Accurate prediction of RNA 5-hydroxymethylcytosine modification by utilizing novel position-specific gapped k-mer descriptors","volume":"18","author":"Ahmed","year":"2020","journal-title":"Comput Struct Biotechnol J"},{"key":"2024090622303213500_btae528-B3","doi-asserted-by":"crossref","first-page":"8491","DOI":"10.1109\/ACCESS.2021.3049146","article-title":"Prediction of RNA 5-hydroxymethylcytosine modifications using deep learning","volume":"9","author":"Ali","year":"2021","journal-title":"IEEE Access"},{"key":"2024090622303213500_btae528-B4","first-page":"2437","article-title":"5-Hydroxymethylation-associated epigenetic modifiers of Alzheimer\u2019s disease modulate Tau-induced neurotoxicity","volume":"25","author":"Bernstein","year":"2016","journal-title":"Hum Mol Genet"},{"key":"2024090622303213500_btae528-B5","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1186\/s13059-016-1112-z","article-title":"DIVAN: accurate identification of non-coding disease-specific risk variants using multi-omics profiles","volume":"17","author":"Chen","year":"2016","journal-title":"Genome Biol"},{"key":"2024090622303213500_btae528-B6","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1186\/s13104-017-2851-y","article-title":"Using DIVAN to assess disease\/trait-associated single nucleotide variants in genome-wide scale","volume":"10","author":"Chen","year":"2017","journal-title":"BMC Res Notes"},{"key":"2024090622303213500_btae528-B7","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1093\/bioinformatics\/btv094","article-title":"A novel statistical method for quantitative comparison of multiple ChIP-seq datasets","volume":"31","author":"Chen","year":"2015","journal-title":"Bioinformatics"},{"key":"2024090622303213500_btae528-B8","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1093\/bioinformatics\/bty872","article-title":"TIVAN: tissue-specific cis-eQTL single nucleotide variant annotation and prediction","volume":"35","author":"Chen","year":"2019","journal-title":"Bioinformatics"},{"key":"2024090622303213500_btae528-B9","doi-asserted-by":"crossref","first-page":"2955","DOI":"10.1093\/hmg\/ddy193","article-title":"5-Hydroxymethylcytosine alterations in the human postmortem brains of autism spectrum disorder","volume":"27","author":"Cheng","year":"2018","journal-title":"Hum Mol Genet"},{"key":"2024090622303213500_btae528-B10","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1016\/j.neurobiolaging.2013.11.031","article-title":"Global changes in DNA methylation and hydroxymethylation in Alzheimer\u2019s disease human brain","volume":"35","author":"Coppieters","year":"2014","journal-title":"Neurobiol Aging"},{"key":"2024090622303213500_btae528-B11","doi-asserted-by":"crossref","first-page":"6161","DOI":"10.1038\/s41467-020-20001-w","article-title":"A human tissue map of 5-hydroxymethylcytosines exhibits tissue specificity through gene and enhancer modulation","volume":"11","author":"Cui","year":"2020","journal-title":"Nat Commun"},{"key":"2024090622303213500_btae528-B12","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1111\/j.1541-0420.2009.01191.x","article-title":"Predictive model assessment for count data","volume":"65","author":"Czado","year":"2009","journal-title":"Biometrics"},{"key":"2024090622303213500_btae528-B13","doi-asserted-by":"crossref","first-page":"11.14.1","DOI":"10.1002\/0471250953.bi1114s51","article-title":"Mapping RNA-seq reads with STAR","volume":"51","author":"Dobin","year":"2015","journal-title":"Curr Protoc Bioinformatics"},{"key":"2024090622303213500_btae528-B14","doi-asserted-by":"crossref","first-page":"3530","DOI":"10.1111\/jcmm.14252","article-title":"5-Hydroxymethylcytosine profiling from genomic and cell-free DNA for colorectal cancers patients","volume":"23","author":"Gao","year":"2019","journal-title":"J Cell Mol Med"},{"key":"2024090622303213500_btae528-B15","doi-asserted-by":"crossref","first-page":"5270","DOI":"10.1038\/s41467-020-18965-w","article-title":"Detection of early stage pancreatic cancer using 5-hydroxymethylcytosine signatures in circulating cell free DNA","volume":"11","author":"Guler","year":"2020","journal-title":"Nat Commun"},{"key":"2024090622303213500_btae528-B16","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1016\/j.molcel.2016.06.028","article-title":"A highly sensitive and robust method for genome-wide 5hmC profiling of rare cell populations","volume":"63","author":"Han","year":"2016","journal-title":"Mol Cell"},{"key":"2024090622303213500_btae528-B17","doi-asserted-by":"crossref","first-page":"4249","DOI":"10.1038\/s41467-021-24425-w","article-title":"Tissue-specific 5-hydroxymethylcytosine landscape of the human genome","volume":"12","author":"He","year":"2021","journal-title":"Nat Commun"},{"key":"2024090622303213500_btae528-B18","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1093\/ilar.53.3-4.232","article-title":"Recruitment and biological consequences of histone modification of H3K27me3 and H3K9me3","volume":"53","author":"Kim","year":"2012","journal-title":"ILAR J"},{"key":"2024090622303213500_btae528-B153","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"3rd International Conference for Learning Representations"},{"key":"2024090622303213500_btae528-B19","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1126\/science.1169786","article-title":"The nuclear DNA base 5-hydroxymethylcytosine is present in Purkinje neurons and the brain","volume":"324","author":"Kriaucionis","year":"2009","journal-title":"Science"},{"key":"2024090622303213500_btae528-B20","doi-asserted-by":"crossref","first-page":"109042","DOI":"10.1016\/j.celrep.2021.109042","article-title":"5-Hydroxymethylcytosine is dynamically regulated during forebrain organoid development and aberrantly altered in Alzheimer\u2019s disease","volume":"35","author":"Kuehner","year":"2021","journal-title":"Cell Rep"},{"key":"2024090622303213500_btae528-B21","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/nature14248","article-title":"Integrative analysis of 111 reference human epigenomes","volume":"518","author":"Kundaje","year":"2015","journal-title":"Nature"},{"key":"2024090622303213500_btae528-B22","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1038\/ng.2802","article-title":"Meta-analysis of 74,046 individuals identifies 11 new susceptibility loci for Alzheimer\u2019s disease","volume":"45","author":"Lambert","year":"2013","journal-title":"Nat Genet"},{"key":"2024090622303213500_btae528-B23","doi-asserted-by":"crossref","first-page":"R25","DOI":"10.1186\/gb-2009-10-3-r25","article-title":"Ultrafast and memory-efficient alignment of short DNA sequences to the human genome","volume":"10","author":"Langmead","year":"2009","journal-title":"Genome Biol"},{"key":"2024090622303213500_btae528-B24","doi-asserted-by":"crossref","first-page":"870726","DOI":"10.4061\/2011\/870726","article-title":"Distribution of 5-hydroxymethylcytosine in different human tissues","volume":"2011","author":"Li","year":"2011","journal-title":"J Nucleic Acids"},{"key":"2024090622303213500_btae528-B25","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1038\/cr.2017.121","article-title":"5-Hydroxymethylcytosine signatures in circulating cell-free DNA as diagnostic biomarkers for human cancers","volume":"27","author":"Li","year":"2017","journal-title":"Cell Res"},{"key":"2024090622303213500_btae528-B26","doi-asserted-by":"crossref","first-page":"15903","DOI":"10.1038\/ncomms15903","article-title":"Ten-eleven translocation 2 interacts with forkhead box O3 and regulates adult neurogenesis","volume":"8","author":"Li","year":"2017","journal-title":"Nat Commun"},{"key":"2024090622303213500_btae528-B27","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1016\/j.cell.2012.07.033","article-title":"Loss of 5-hydroxymethylcytosine is an epigenetic hallmark of melanoma","volume":"150","author":"Lian","year":"2012","journal-title":"Cell"},{"key":"2024090622303213500_btae528-B28","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1038\/ng.3766","article-title":"Case-control association mapping by proxy using family history of disease","volume":"49","author":"Liu","year":"2017","journal-title":"Nat Genet"},{"key":"2024090622303213500_btae528-B29","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1186\/s13059-014-0550-8","article-title":"Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2","volume":"15","author":"Love","year":"2014","journal-title":"Genome Biol"},{"key":"2024090622303213500_btae528-B154","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1016\/j.cell.2012.11.022","article-title":"MeCP2 binds to 5hmC enriched within active genes and accessible chromatin in the nervous system","volume":"151","author":"Mell\u00e9n","year":"2012","journal-title":"Cell"},{"key":"2024090622303213500_btae528-B30","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1186\/s40168-021-01061-6","article-title":"Gut microbiome variation modulates the effects of dietary fiber on host metabolism","volume":"9","author":"Murga-Garrido","year":"2021","journal-title":"Microbiome"},{"key":"2024090622303213500_btae528-B31","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1158\/2643-3230.BCD-21-0143","article-title":"The cell type-specific 5hmC landscape and dynamics of healthy human hematopoiesis and TET2-mutant preleukemia","volume":"3","author":"Nakauchi","year":"2022","journal-title":"Blood Cancer Discov"},{"key":"2024090622303213500_btae528-B152","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"2024090622303213500_btae528-B32","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1093\/hmg\/ddz273","article-title":"Ethnicity-specific and overlapping alterations of brain hydroxymethylome in Alzheimer\u2019s disease","volume":"29","author":"Qin","year":"2020","journal-title":"Hum Mol Genet"},{"key":"2024090622303213500_btae528-B33","doi-asserted-by":"crossref","first-page":"12410","DOI":"10.1038\/s41598-022-16685-3","article-title":"Cell-free DNA 5-hydroxymethylcytosine is an emerging marker of acute myeloid leukemia","volume":"12","author":"Shao","year":"2022","journal-title":"Sci Rep"},{"key":"2024090622303213500_btae528-B34","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nbt.1732","article-title":"Selective chemical labeling reveals the genome-wide distribution of 5-hydroxymethylcytosine","volume":"29","author":"Song","year":"2011","journal-title":"Nat Biotechnol"},{"key":"2024090622303213500_btae528-B35","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1038\/cr.2017.106","article-title":"5-Hydroxymethylcytosine signatures in cell-free DNA provide information about tumor types and stages","volume":"27","author":"Song","year":"2017","journal-title":"Cell Res"},{"key":"2024090622303213500_btae528-B36","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1016\/j.cell.2013.02.004","article-title":"Dynamic readers for 5-(hydroxy)methylcytosine and its oxidized derivatives","volume":"152","author":"Spruijt","year":"2013","journal-title":"Cell"},{"key":"2024090622303213500_btae528-B37","doi-asserted-by":"crossref","first-page":"176","DOI":"10.3390\/dermatopathology8020023","article-title":"5-Hydroxymethylcytosine loss in conjunctival melanoma","volume":"8","author":"Stahl","year":"2021","journal-title":"Dermatopathology (Basel)"},{"key":"2024090622303213500_btae528-B38","doi-asserted-by":"crossref","first-page":"R54","DOI":"10.1186\/gb-2011-12-6-r54","article-title":"5-Hydroxymethylcytosine is associated with enhancers and gene bodies in human embryonic stem cells","volume":"12","author":"Stroud","year":"2011","journal-title":"Genome Biol"},{"key":"2024090622303213500_btae528-B39","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1126\/science.1170116","article-title":"Conversion of 5-methylcytosine to 5-hydroxymethylcytosine in mammalian DNA by MLL partner TET1","volume":"324","author":"Tahiliani","year":"2009","journal-title":"Science"},{"key":"2024090622303213500_btae528-B40","doi-asserted-by":"crossref","first-page":"3641","DOI":"10.1093\/hmg\/ddt214","article-title":"Genome-wide loss of 5-hmC is a novel epigenetic feature of Huntington\u2019s disease","volume":"22","author":"Wang","year":"2013","journal-title":"Hum Mol Genet"},{"key":"2024090622303213500_btae528-B41","doi-asserted-by":"crossref","first-page":"5340","DOI":"10.1093\/bioinformatics\/btac696","article-title":"DeepPerVar: a multi-modal deep learning framework for functional interpretation of genetic variants in personal genome","volume":"38","author":"Wang","year":"2022","journal-title":"Bioinformatics"},{"key":"2024090622303213500_btae528-B42","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1038\/ng1598","article-title":"Chromosome-wide and promoter-specific analyses identify sites of differential DNA methylation in normal and transformed human cells","volume":"37","author":"Weber","year":"2005","journal-title":"Nat Genet"},{"key":"2024090622303213500_btae528-B151","article-title":"Multi-modal factorized bilinear pooling with co-attention learning for visual question answering","author":"Yu","year":"2017","journal-title":"ICCV"},{"key":"2024090622303213500_btae528-B43","doi-asserted-by":"crossref","first-page":"R137","DOI":"10.1186\/gb-2008-9-9-r137","article-title":"Model-based analysis of ChIP-Seq (MACS)","volume":"9","author":"Zhang","year":"2008","journal-title":"Genome Biol"},{"key":"2024090622303213500_btae528-B44","doi-asserted-by":"crossref","first-page":"603686","DOI":"10.3389\/fonc.2021.603686","article-title":"Loss of 5-hydroxymethylcytosine as an epigenetic signature that correlates with poor outcomes in patients with medulloblastoma","volume":"11","author":"Zhao","year":"2021","journal-title":"Front Oncol"},{"key":"2024090622303213500_btae528-B45","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning-based sequence model","volume":"12","author":"Zhou","year":"2015","journal-title":"Nat Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae528\/58942459\/btae528.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/9\/btae528\/59036427\/btae528.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/9\/btae528\/59036427\/btae528.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T05:06:37Z","timestamp":1732683997000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae528\/7743210"}},"subtitle":[],"editor":[{"given":"Macha","family":"Nikolski","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":49,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae528","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.03.04.583444","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,8,28]]},"article-number":"btae528"}}